Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1556 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.8221. Min Act: -0.0000

Data Index: 848865 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7886. Min Act: -0.0001

Data Index: 551687 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.8249. Min Act: -0.0001

Data Index: 598198 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7940. Min Act: -0.0001

Data Index: 46575 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.8250. Min Act: -0.0001

Data Index: 1214417 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7485. Min Act: -0.0001

Data Index: 89328 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7125. Min Act: -0.0001

Data Index: 153481 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6449. Min Act: -0.0001

Data Index: 386277 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6355. Min Act: -0.0001

Data Index: 780972 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6011. Min Act: -0.0001

Data Index: 710903 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6300. Min Act: -0.0001

Data Index: 465203 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.5951. Min Act: -0.0001

Data Index: 1300376 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6188. Min Act: -0.0001

Data Index: 148247 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6017. Min Act: -0.0001

Data Index: 135782 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.5999. Min Act: -0.0001

Data Index: 1622528 (Python Code)

Max Activating Token Index: 958

Text #15

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.5966. Min Act: -0.0001

Data Index: 1070690 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.5901. Min Act: -0.0001

Data Index: 830395 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.5939. Min Act: -0.0001

Data Index: 674211 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.5574. Min Act: -0.0001

Data Index: 1121106 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6121. Min Act: -0.0001

Data Index: 649874 (C4 (Web Text))

Max Activating Token Index: 294